feat: Qualification Matrix + QuickSpecs bundles (#5)

scrape/bundles.py

@@ -39,9 +39,10 @@ class BundleSpec:
     title: str
     version: str | None
     product: str  # e.g. "User Manual", "Release Notes", "Deployment Guide"
-    mode: str    # "toc" or "single"
+    mode: str    # "toc", "single", or "html-file" (committed fixture under scrape/quickspecs/)
     platform: str | None = None
     language: str = "en-US"
+    source_url: str | None = None   # overrides the default support.hpe.com URL
 
 
 # Declared bundles. Versions confirmed 2026-05-22 by probing the docId
@@ -54,6 +55,14 @@ BUNDLES: list[BundleSpec] = [
     BundleSpec("hvm_release_notes_8_1_1", "sd00007609en_us", "HPE Morpheus VM Essentials Software Release Notes",  "8.1.1", "Release Notes",   "single"),
     BundleSpec("hvm_release_notes_8_1_2", "sd00007734en_us", "HPE Morpheus VM Essentials Software Release Notes",  "8.1.2", "Release Notes",   "single"),
     BundleSpec("hvm_deployment_guide",    "sd00007332en_us", "HPE Morpheus VM Essentials Deployment Guide",        None,    "Deployment Guide","toc"),
+    BundleSpec("hvm_qualification_matrix","sd00006551en_us", "Qualification Matrix for HVM Clusters Managed by HPE Morpheus Software", None, "Qualification Matrix", "toc"),
+    # QuickSpecs is a static-HTML fixture (www.hpe.com edge drops automated
+    # connections — see scrape/quickspecs/README.md). doc_id = the QuickSpecs
+    # PSNow ref (a50004260enw). page_count is 1; source_url points at the
+    # public PSNow URL.
+    BundleSpec("hvm_quickspecs", "a50004260enw", "HPE Morpheus VM Essentials Software QuickSpecs",
+               "v4-2026-02-02", "QuickSpecs", "html-file",
+               source_url="https://www.hpe.com/psnow/doc/a50004260enw"),
 ]
 
 
@@ -118,6 +127,24 @@ def _parse_abstract(html: str) -> dict[str, str]:
 
 
 def discover_bundle(s: requests.Session, spec: BundleSpec) -> dict[str, Any]:
+    # html-file bundles are static fixtures — no upstream fetch.
+    if spec.mode == "html-file":
+        return {
+            "slug": spec.slug,
+            "doc_id": spec.doc_id,
+            "title": spec.title,
+            "version": spec.version,
+            "platform": spec.platform,
+            "product": spec.product,
+            "language": spec.language,
+            "page_count": 1,
+            "mode": "html-file",
+            "abstract": "",
+            "dates": {},
+            "landing_page": spec.doc_id,
+            "source_url": spec.source_url or f"https://www.hpe.com/psnow/doc/{spec.doc_id}",
+        }
+
     abstract_html = _get(s, f"{API}/{spec.doc_id}", expect_json=False)
     meta = _parse_abstract(abstract_html or "")
 
@@ -146,7 +173,7 @@ def discover_bundle(s: requests.Session, spec: BundleSpec) -> dict[str, Any]:
         "abstract": meta.get("abstract", ""),
         "dates": {"Published": meta.get("published", "")},
         "landing_page": landing,
-        "source_url": DOC_URL.format(doc_id=spec.doc_id),
+        "source_url": spec.source_url or DOC_URL.format(doc_id=spec.doc_id),
     }
 
 

scrape/quickspecs.py

@@ -0,0 +1,194 @@
+"""Scrape HPE QuickSpecs collateral pages into corpus markdown.
+
+HPE QuickSpecs live at `https://www.hpe.com/us/en/collaterals/collateral.<doc_id>.html`
+with a server-rendered HTML body (confirmed 2026-05-22 by inspecting the
+captured DOM). The blocker for automated scraping is `www.hpe.com`'s
+edge bot defense, which drops connections from non-browser TLS
+fingerprints (curl, wget, Python-urllib, even WebFetch). Bypassed here
+by `curl_cffi` impersonating Chrome 120's JA3/JA4 fingerprint.
+
+Content extraction uses these stable CSS selectors found in the page:
+
+  .lr-right-rail hpe-highlights-container .collateral-content
+       — one per section ("Overview", "Standard Features", etc.)
+  h3.txto-title          — section title
+  div.txto-description   — section body
+  uc-table.uc-table-polaris   — SKU / version-history tables
+
+A committed HTML fixture at `scrape/quickspecs/<doc_id>.html` is used
+as a fallback when the live fetch fails (HPE edge churn, network
+issues). Keeping a current fixture in the repo also makes diffing
+QuickSpecs revisions easy.
+
+Usage (called by scrape.runner for bundles with mode="quickspecs"):
+
+    python -m scrape.quickspecs a50004260enw
+
+Or programmatically:
+
+    from scrape.quickspecs import scrape_quickspecs
+    scrape_quickspecs("a50004260enw", bundle_id="hvm_quickspecs", title="...")
+"""
+from __future__ import annotations
+
+import argparse
+import json
+import logging
+import sys
+from pathlib import Path
+
+from bs4 import BeautifulSoup, NavigableString
+from markdownify import markdownify as md
+
+log = logging.getLogger(__name__)
+
+ROOT = Path(__file__).resolve().parent.parent
+SOURCE_DIR = ROOT / "scrape" / "quickspecs"
+CORPUS_DIR = ROOT / "corpus"
+
+COLLATERAL_URL = "https://www.hpe.com/us/en/collaterals/collateral.{doc_id}.html"
+
+
+def fetch_live(doc_id: str, timeout: float = 30.0) -> str | None:
+    """GET the collateral page via curl_cffi (Chrome 120 TLS fingerprint).
+    Returns the HTML body on success, None on any failure."""
+    try:
+        from curl_cffi import requests as cc
+    except ImportError:
+        log.warning("curl_cffi not installed; can't fetch QuickSpecs live")
+        return None
+    try:
+        r = cc.get(COLLATERAL_URL.format(doc_id=doc_id),
+                   impersonate="chrome120", timeout=timeout)
+        if r.status_code != 200 or not r.text:
+            log.warning("QuickSpecs %s: http=%s bytes=%d", doc_id, r.status_code, len(r.text or ""))
+            return None
+        return r.text
+    except Exception as e:
+        log.warning("QuickSpecs %s live fetch failed: %s", doc_id, e)
+        return None
+
+
+def fetch_fixture(doc_id: str) -> str | None:
+    """Read the committed HTML fixture as fallback."""
+    p = SOURCE_DIR / f"{doc_id}.html"
+    if not p.exists():
+        return None
+    return p.read_text()
+
+
+def _extract_content_blocks(html: str) -> list[str]:
+    """Pull each section block (.collateral-content under .lr-right-rail).
+
+    The fixture format (just .quickspecs-content wrapper) and the live
+    format (.lr-right-rail with nested hpe-highlights-container) are
+    both supported. Returns a list of section HTML strings, in document
+    order.
+    """
+    soup = BeautifulSoup(html, "html.parser")
+    # Live format: each <hpe-highlights-container> under .lr-right-rail has
+    # one or more .collateral-content blocks; concat them.
+    rail = soup.select_one(".lr-right-rail")
+    if rail is not None:
+        blocks = rail.select(".collateral-content")
+        return [str(b) for b in blocks]
+    # Fixture format: a single wrapper holding all the H2/H3 sections.
+    wrapper = soup.select_one(".quickspecs-content")
+    if wrapper is not None:
+        return [str(wrapper)]
+    # Last-resort: whole body.
+    body = soup.body or soup
+    return [str(body)]
+
+
+def parse_html(html: str) -> str:
+    """Convert QuickSpecs HTML to clean markdown.
+
+    Filters out the page chrome (nav, footer, recommendations carousel,
+    cookie banner, analytics blobs) by extracting only the content
+    blocks, then runs markdownify."""
+    blocks = _extract_content_blocks(html)
+    chunks: list[str] = []
+    for block in blocks:
+        soup = BeautifulSoup(block, "html.parser")
+        # Drop anchor placeholders that markdownify turns into noisy links
+        for a in soup.select('[hpe-left-rail-anchor]'):
+            a.decompose()
+        # Drop carousel / share / recommendation widgets if any leaked in.
+        for sel in ("esl-share", "hpe-recommendations", "hpe-sticky-bar",
+                    "esl-scrollbar", "esl-trigger", "video-overlay",
+                    "generic-modal-loader", "style", "script"):
+            for el in soup.select(sel):
+                el.decompose()
+        chunks.append(md(str(soup), heading_style="ATX", bullets="-",
+                          strip=["span", "div"]))
+    text = "\n\n".join(chunks)
+    # Collapse runs of blank lines markdownify likes to emit.
+    text = "\n".join(line.rstrip() for line in text.splitlines())
+    while "\n\n\n" in text:
+        text = text.replace("\n\n\n", "\n\n")
+    return text.strip() + "\n"
+
+
+def scrape_quickspecs(doc_id: str, bundle_id: str, title: str,
+                     version: str | None = None,
+                     product: str = "QuickSpecs",
+                     source_url: str | None = None,
+                     force: bool = False) -> bool:
+    """Live-fetch (or fall back to fixture), parse, write corpus files.
+
+    Returns True if files were written, False if skipped (already exists
+    and --force not set)."""
+    bundle_dir = CORPUS_DIR / bundle_id
+    md_path = bundle_dir / f"{doc_id}.md"
+    json_path = bundle_dir / f"{doc_id}.json"
+    if not force and md_path.exists() and json_path.exists():
+        log.info("  %s/%s: already on disk (use --force to refresh)", bundle_id, doc_id)
+        return False
+
+    html = fetch_live(doc_id)
+    fetched_from = "live"
+    if html is None:
+        html = fetch_fixture(doc_id)
+        fetched_from = "fixture"
+    if html is None:
+        log.error("QuickSpecs %s: no live response and no fixture at %s",
+                  doc_id, SOURCE_DIR / f"{doc_id}.html")
+        return False
+
+    body_md = parse_html(html)
+    bundle_dir.mkdir(parents=True, exist_ok=True)
+    md_path.write_text(body_md)
+    sidecar = {
+        "bundle_id": bundle_id,
+        "page_id": doc_id,
+        "title": title,
+        "ordinal": 1,
+        "parent_title": None,
+        "doc_id": doc_id,
+        "version": version,
+        "product": product,
+        "source_url": source_url or f"https://www.hpe.com/psnow/doc/{doc_id}",
+        "fetched_from": fetched_from,
+    }
+    json_path.write_text(json.dumps(sidecar, indent=2) + "\n")
+    log.info("  %s/%s: %d bytes from %s", bundle_id, doc_id, len(body_md), fetched_from)
+    return True
+
+
+def main() -> int:
+    logging.basicConfig(level=logging.INFO, format="%(message)s")
+    p = argparse.ArgumentParser()
+    p.add_argument("doc_id", help="QuickSpecs document id, e.g. a50004260enw")
+    p.add_argument("--bundle-id", default="hvm_quickspecs")
+    p.add_argument("--title", default="HPE Morpheus VM Essentials Software QuickSpecs")
+    p.add_argument("--version", default=None)
+    p.add_argument("--force", action="store_true")
+    args = p.parse_args()
+    ok = scrape_quickspecs(args.doc_id, args.bundle_id, args.title,
+                            args.version, force=args.force)
+    return 0 if ok else 1
+
+
+if __name__ == "__main__":
+    sys.exit(main())

scrape/quickspecs/README.md

@@ -0,0 +1,27 @@
+# scrape/quickspecs/
+
+Static HTML fixtures for HPE QuickSpecs documents that aren't reachable
+from the runner (www.hpe.com edge drops connections from datacenter IPs
+with non-browser User-Agents — verified 2026-05-22 with curl, wget, and
+Anthropic's WebFetch).
+
+## Workflow
+
+1. Operator visits `https://www.hpe.com/psnow/doc/<doc_id>` in a real
+   browser, opens DevTools → Elements → Copy the `<body>` HTML.
+2. Save it at `scrape/quickspecs/<doc_id>.html`.
+3. Add a bundle entry in `scrape/bundles.py` with `mode="html-file"`.
+4. `python -m scrape.runner --bundle hvm_quickspecs --force` reads the
+   committed HTML and writes `corpus/hvm_quickspecs/<doc_id>.{md,json}`.
+5. Re-index and ship.
+
+QuickSpecs only update every few months (HPE rebrand, new SKU added,
+feature change). When a new version drops, refresh the local HTML
+file and re-run the scrape.
+
+## Current fixtures
+
+- `a50004260enw.html` — HPE Morpheus VM Essentials Software QuickSpecs
+  (Version 4, 02-February-2026). SKUs: S5Q81AAE (1-yr), S5Q82AAE
+  (3-yr), S5Q83AAE (5-yr) — all "per Socket E-LTU" with Tech Care
+  Essentials included.

scrape/quickspecs/a50004260enw.html

@@ -0,0 +1,219 @@
+<!-- Source: https://www.hpe.com/us/en/collaterals/collateral.a50004260enw.html
+     Captured: 2026-05-22 (Version 4, 02-February-2026)
+     Reason for static fixture: www.hpe.com edge drops connections from
+     datacenter IPs / non-browser User-Agents. Operator captures the
+     .lr-right-rail HTML in a browser and commits it here.
+     Parser: python -m scrape.quickspecs_parse a50004260enw -->
+<div class="quickspecs-content">
+ <h1>HPE Morpheus VM Essentials Software QuickSpecs</h1>
+ <p><em>Version 4 — 02-February-2026 — a50004260enw</em></p>
+ <p><strong>HPE Morpheus VM Essentials Software is a virtualization
+ software solution that allows customers to provision and manage KVM
+ and VMware-based VMs from a single intuitive interface.</strong></p>
+
+ <h2 id="overview">Overview</h2>
+ <p>The solution comes with the KVM-based HVM hypervisor that is enhanced
+ to include enterprise-grade cluster management with capabilities such
+ as high availability, live compute and storage migration, distributed
+ workload placement, integrated data protection, secure hardening, and
+ external storage support. To enable flexibility for those continuing to
+ host VMware-based applications, VM Essentials can also be used to
+ connect to and manage existing VMware clusters. This means unified
+ management and simple VM provisioning across both the HVM hypervisor
+ and VMware ESXi™ so you can provision workloads on demand to the right
+ environment, on your terms, with zero lock-in. When you're ready, you
+ can use the included toolset to convert existing VMware images to
+ VM Essentials.</p>
+
+ <h3>Validated Hardware and Software</h3>
+ <p>The list of validated compute and storage hardware for VM Essentials
+ can be found in the <a href="https://www.hpe.com/support/VME-Compatibility-Matrix">compatibility matrix</a>,
+ along with validated operating systems and ISV software.</p>
+
+ <h3>Models</h3>
+ <p>Hewlett Packard Enterprise is making the following VM Essentials
+ SKUs available. VM Essentials SKUs are licensed per physical CPU
+ socket. Each SKU includes Tech Care Essentials support.</p>
+
+ <table>
+  <caption>HPE Morpheus VM Essentials Software SKUs</caption>
+  <thead><tr><th>Description</th><th>SKU</th></tr></thead>
+  <tbody>
+   <tr><td>HPE Morpheus VM Essentials Software per Socket 1-year E-LTU</td><td><code>S5Q81AAE</code></td></tr>
+   <tr><td>HPE Morpheus VM Essentials Software per Socket 3-year E-LTU</td><td><code>S5Q82AAE</code></td></tr>
+   <tr><td>HPE Morpheus VM Essentials Software per Socket 5-year E-LTU</td><td><code>S5Q83AAE</code></td></tr>
+  </tbody>
+ </table>
+
+ <h2 id="standard-features">Standard Features</h2>
+
+ <h3>Key Features</h3>
+
+ <h4>Enterprise Virtualization</h4>
+ <ul>
+  <li><strong>VM Live Migration:</strong> Migrate running virtual
+  machines from one physical host to another within an HVM cluster
+  without downtime to improve host utilization or to perform host
+  maintenance.</li>
+  <li><strong>VM High Availability:</strong> Enable workload resiliency
+  with virtual machine high availability to quickly restart virtual
+  machines on another physical host in the event of a host failure.</li>
+  <li><strong>Distributed Workload Placement:</strong> Dynamically
+  schedule the placement of virtual machines within an HVM cluster
+  based on intelligent placement logic that determines the optimal host
+  for the virtual machine.</li>
+  <li><strong>VM Live Storage Migration:</strong> Migrate a running
+  virtual machine's storage disks from one datastore to another without
+  downtime.</li>
+  <li><strong>External Storage Support:</strong> Integrate with existing
+  external storage (NFS, iSCSI, Fibre Channel) to take advantage of
+  existing infrastructure investments.</li>
+ </ul>
+
+ <h4>Solution Integrations</h4>
+ <ul>
+  <li><strong>VMware vSphere Integration:</strong> Integrate VM
+  Essentials with a vSphere deployment to discover existing virtual
+  machines, provision new virtual machines, as well as manage
+  provisioned or discovered machines.</li>
+  <li><strong>Native IP Pools:</strong> Assign virtual machine IP
+  addresses using the VM Essentials native IP pools feature to define
+  and manage pools of IP addresses associated with virtual machine
+  networks.</li>
+  <li><strong>Native Secrets Management:</strong> Securely store and
+  retrieve credentials and other sensitive information used in
+  automation tasks for bootstrapping and managing managed virtual
+  machines.</li>
+  <li><strong>IP Address Management (IPAM) Integration:</strong>
+  Integrate 3rd party IPAM solutions (InfoBlox, BlueCat, SolarWinds,
+  phpIPAM, EfficientIP) to automate the reservation and assignment of
+  IP address.</li>
+  <li><strong>Domain Name System (DNS) Integration:</strong> Integrate
+  3rd party DNS solutions (PowerDNS, Microsoft DNS, BlueCat, InfoBlox,
+  EfficientIP) to automate the creation of DNS A and PTR records.</li>
+  <li><strong>Native Data Protection:</strong> Create and restore
+  snapshot-based backups for VM Essentials and VMware virtual machines
+  using the native data protection functionality.</li>
+  <li><strong>Data Protection Integration:</strong> Integrate 3rd party
+  Data Protection solutions (Commvault, Rubrik, Veeam) to create backup
+  jobs during the creation of a VMware virtual machine and restore
+  backups through the VM Essentials web interface.</li>
+  <li><strong>Provisioning Task Automation:</strong> Execute automation
+  scripts (Bash and PowerShell) during the provisioning of virtual
+  machines to orchestrate bootstrap operations such as software
+  installation and system configuration.</li>
+  <li><strong>HPE Alletra Storage MP Integration:</strong> Integrate
+  with the HPE Alletra Storage MP B10000 storage array to utilize
+  direct virtual machine volume mapping to the storage array to enable
+  granular performance configuration and array-based snapshotting.</li>
+ </ul>
+
+ <h3>Virtual Machine Management</h3>
+ <ul>
+  <li><strong>Power Operations:</strong> Start, stop, and restart
+  VMware and HVM virtual machines.</li>
+  <li><strong>Snapshot Management:</strong> Create, revert, and delete
+  virtual machine snapshots for VMware and HVM virtual machines.</li>
+  <li><strong>Virtual Hardware Management:</strong> Add and remove
+  virtual hardware such as hard disks, network interfaces, CPU and
+  memory from a managed virtual machine (VM Essentials or VMware).</li>
+  <li><strong>Integrated Backup Management:</strong> Create, restore,
+  and delete virtual machine backups for VMware and HVM virtual
+  machines.</li>
+  <li><strong>HTML5 Console:</strong> Access the console of managed
+  virtual machines via the VM Essentials manager web interface with
+  support for Virtual Network Computing (VNC), Secure Shell (SSH), and
+  Remote Desktop Protocol (RDP).</li>
+  <li><strong>Day 2 Task Automation:</strong> Execute automation
+  scripts (Bash and PowerShell) against managed virtual machines to
+  perform day 2 operational tasks such as freeing up disk space or
+  updating system packages.</li>
+  <li><strong>Tag Management:</strong> Create and manage virtual
+  machine tags for VMware and VM Essentials virtual machines.</li>
+ </ul>
+
+ <h2 id="service-and-support">Service and Support</h2>
+
+ <h3>HPE Services</h3>
+ <p>No matter where you are in your digital transformation journey, you
+ can count on HPE Services to deliver the expertise you need when, where
+ and how you need it. From planning to deployment, ongoing operations
+ and beyond, our experts can help you realize your digital ambitions.
+ See <a href="https://www.hpe.com/services">https://www.hpe.com/services</a>.</p>
+
+ <h3>HPE Complete Care Service</h3>
+ <p>A modular, edge-to-cloud IT environment service designed to help
+ optimize your entire IT environment and achieve agreed-upon IT outcomes
+ and business goals through a personalized experience. Includes complete
+ coverage, an assigned HPE team, modular engagement, enhanced incident
+ management with priority access, and AI-driven customer experience.
+ See <a href="https://www.hpe.com/services/completecare">https://www.hpe.com/services/completecare</a>.</p>
+
+ <h3>HPE Tech Care Service</h3>
+ <p>Operational support service experience for HPE products. Goes beyond
+ traditional support by providing access to product-specific experts,
+ an AI-driven digital experience, and general technical guidance.
+ Available in three response levels:</p>
+ <ul>
+  <li><strong>Basic:</strong> 9×5 business hours, 2-hour response.</li>
+  <li><strong>Essential:</strong> 15-minute response 24×7 (most
+  enterprise customers).</li>
+  <li><strong>Critical:</strong> 6-hour repair commitment where
+  available, plus outage management response for severity 1
+  incidents.</li>
+ </ul>
+ <p>See <a href="https://www.hpe.com/services/techcare">https://www.hpe.com/services/techcare</a>.</p>
+
+ <h3>HPE Lifecycle Services</h3>
+ <ul>
+  <li>Lifecycle Install and Startup Services.</li>
+  <li>Firmware Update Analysis Service.</li>
+  <li>Firmware Update Implementation Service.</li>
+  <li>Implementation assistance services.</li>
+  <li>HPE Service Credits.</li>
+ </ul>
+ <p>See <a href="https://www.hpe.com/services/lifecycle">https://www.hpe.com/services/lifecycle</a>.</p>
+
+ <h3>Other Related Services</h3>
+ <ul>
+  <li><strong>HPE Education Services:</strong> Training and
+  certification. See <a href="https://www.hpe.com/services/training">https://www.hpe.com/services/training</a>.</li>
+  <li><strong>Defective Media Retention:</strong> Available with
+  Complete Care and Tech Care for disks/SSDs replaced due to
+  malfunction.</li>
+  <li><strong>Parts and Materials:</strong> HPE provides supported
+  replacement parts including engineering improvements; parts past
+  maximum supported lifetime are not provided.</li>
+  <li><strong>How to Purchase:</strong> Services sold by HPE and HPE
+  Authorized Service Partners. Customers from commercial resellers see
+  <a href="https://ssc.hpe.com/portal/site/ssc/">ssc.hpe.com</a>.</li>
+ </ul>
+
+ <h3>AI Powered and Digitally Enabled Support Experience</h3>
+ <p>Sign into the HPE Support Center for streamlined self-serve case
+ creation, knowledge recommendations, personalized task alerts, and an
+ intelligent virtual agent with seamless transition to a live support
+ agent when needed.
+ See <a href="https://support.hpe.com/hpesc/public/home/signin">support.hpe.com</a>.</p>
+
+ <h3>Consume IT On Your Terms</h3>
+ <p><a href="https://www.hpe.com/GreenLake">HPE GreenLake</a>
+ edge-to-cloud platform brings the cloud experience directly to your
+ apps and data — at the edge, in colocations, or in your data center.
+ Pay-per-use, scalable, self-service experience.</p>
+
+ <h2 id="summary-of-changes">Summary of Changes</h2>
+ <table>
+  <thead><tr><th>Date</th><th>Version</th><th>Action</th><th>Description</th></tr></thead>
+  <tbody>
+   <tr><td>02-Feb-2026</td><td>Version 4</td><td>Changed</td><td>HPE Rebranding applied</td></tr>
+   <tr><td>05-May-2025</td><td>Version 3</td><td>Changed</td><td>Branding updates, Overview and Standard Features sections updated.</td></tr>
+   <tr><td>13-Jan-2025</td><td>Version 2</td><td>Changed</td><td>Overview and Standard Features sections updated.</td></tr>
+   <tr><td>02-Dec-2024</td><td>Version 1</td><td>New</td><td>New QuickSpecs.</td></tr>
+  </tbody>
+ </table>
+
+ <hr />
+ <p><em>© Copyright 2026 Hewlett Packard Enterprise Development LP.
+ a50004260enw, 16864 - Worldwide - V4 - 02-February-2026.</em></p>
+</div>

scrape/runner.py

@@ -307,8 +307,22 @@ def main() -> int:
     s = _session()
     total = 0
     for b in bundles:
-        if b.get("mode") == "single":
+        mode = b.get("mode")
+        if mode == "single":
             total += scrape_single_bundle(s, b, args.force)
+        elif mode == "html-file":
+            # Live-scrape HPE collateral (QuickSpecs) via curl_cffi; falls back
+            # to scrape/quickspecs/<doc_id>.html fixture if the edge blocks us.
+            from scrape.quickspecs import scrape_quickspecs
+            ok = scrape_quickspecs(
+                doc_id=b["doc_id"], bundle_id=b["slug"],
+                title=b.get("title", b["doc_id"]),
+                version=b.get("version"),
+                product=b.get("product", "QuickSpecs"),
+                source_url=b.get("source_url"),
+                force=args.force,
+            )
+            total += 1 if ok else 0
         else:
             total += scrape_toc_bundle(s, b, args.force, args.concurrency)
     print(f"scraped {total} new/updated pages", file=sys.stderr)